>
Fa   |   Ar   |   En
   Spectral clustering on gene expression profile to identify cancer types or subtypes  
   
نویسنده chin a.j. ,mirzal a. ,haron h.
منبع jurnal teknologi - 2015 - دوره : 76 - شماره : 1 - صفحه:289 -297
چکیده    Gene expression profile is eminent for its broad applications and achievements in disease discovery and analysis,especially in cancer research. spectral clustering is robust to irrelevant features which are appropriated for gene expression analysis. however,previous works show that performance comparison with other clustering methods is limited and only a few microarray data sets were analyzed in each study. in this study,we demonstrate the use of spectral clustering in identifying cancer types or subtypes from microarray gene expression profiling. spectral clustering was applied to eleven microarray data sets and its clustering performances were compared with the results in the literature. based on the result,overall the spectral clustering slightly outperformed the corresponding results in the literature. the spectral clustering can also offer more stable clustering performances as it has smaller standard deviation value. moreover,out of eleven data sets the spectral clustering outperformed the corresponding methods in the literature for six data sets. so,it can be stated that the spectral clustering is a promising method in identifying the cancer types or subtypes for microarray gene expression data sets. © 2015 penerbit utm press. all rights reserved.
کلیدواژه Cancer; Gaussian kernel; Microarray gene expression; Spectral clustering; Tumor
آدرس department of computer science,universiti teknologi malaysia,johor bahru, Malaysia, computer science department,college of arts and applied sciences,dhofar university, Oman, department of computer science,universiti teknologi malaysia,johor bahru, Malaysia
 
     
   
Authors
  
 
 

Copyright 2023
Islamic World Science Citation Center
All Rights Reserved